Re: [NFS] NFS Client in 2.2.13 (eepro100 problem)

Trond Myklebust (trond.myklebust@fys.uio.no)
23 Nov 1999 12:13:13 +0100


>>>>> " " == slack <jhansen@xmission.com> writes:

> I've got a Linux mail server mounting /home from a NetApp F720.

> Client: Dual PIII 500 with 512MB ram. Linux mail 2.2.13 #11
> SMP Fri Nov 19 16:56:29 MST 1999 i686 unknown Using
> nfs-utils-0.1.2. Intel EtherExpress Pro 100+ w/ driver vserion
> 1.09l. Full duplex 100mbit. Mount options:
^^^^^^

> NetApp:
> Release 5.2.3D1: Tue Aug 17 13:35:10 PDT 1999 slot 0:
> System Board (NetApp System Board V L0)
> Model Name: F720 Firmware release: 2.2_a2
> Memory Size: 256 MB

> The problem is, that under high access to the /home mount RPC
> gets congested, with error "nfs: task 29025 can't get a request
> slot" and NFS processes will start to block. In some cases

I have the exact same problem with the EEpro100 1.09j driver. It makes
testing on the linux-2.3.x series a major pain.

Please try with the stock 1.06 from linux-2.2.13. It seems to be a lot
more stable under high load.

Cheers,
Trond

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/